quickstart

1. get an api key

sign in to the rumik dashboard, open api keys, and create a new key. the full key is shown only once at creation, so copy it somewhere safe before closing the dialog.

generate an api key

create and manage keys in your dashboard.

2. pick a model

every request takes a model and text. muga is our more expressive model; mulberry is faster. each is steered differently. see the prompting guides for muga and mulberry for the full breakdown.

model	steer with
`muga`	a tone tag prefix, e.g. `[happy]`
`mulberry`	a natural-language `description` (+ `speaker`)

3. synthesize speech

pass your key as a bearer token. when audio_format is omitted, the response body is a 24 khz mono wav.

curl -X POST https://silk-api.rumik.ai/v1/tts \
  -H "Authorization: Bearer rk_live_•••••••••" \
  -H "Content-Type: application/json" \
  -d '{ "model": "muga", "text": "[happy] Namaste! Kaise hain aap?" }' \
  --output speech.wav

import requests

API_KEY = "rk_live_•••••••••"
BASE = "https://silk-api.rumik.ai"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}

# muga: expressive hinglish, tone set via a [tone] prefix on the text
# tones: neutral (default), happy, sad, excited, angry, whisper
r = requests.post(f"{BASE}/v1/tts", headers=HEADERS, json={
    "model": "muga",
    "text": "[happy] Namaste! Kaise hain aap?",
})
r.raise_for_status()
open("muga.wav", "wb").write(r.content)        # 24 kHz mono WAV

# mulberry: steered by a description (+ optional named voice)
r = requests.post(f"{BASE}/v1/tts", headers=HEADERS, json={
    "model": "mulberry",
    "text": "Hi there, how can I help you today?",
    "description": "a warm 30s female voice, smooth timbre, conversational pacing, like a friendly assistant",
    "speaker": "siya",   # optional named voice: siya, ira, adam, emma, …
})
r.raise_for_status()
open("mulberry.wav", "wb").write(r.content)

choose another audio format

set audio_format to opus, pcm, mulaw, alaw, or mp3. for example, this returns opus in an ogg container:

curl

api_key='rk_live_•••••••••'

curl --request POST https://silk-api.rumik.ai/v1/tts \
  --header "Authorization: Bearer ${api_key}" \
  --header "content-type: application/json" \
  --data '{"model":"muga","text":"[happy] namaste! kaise hain aap?","audio_format":"opus"}' \
  --output speech.ogg

omit the field for wav. do not send "audio_format": null. see audio formats for binary http, json base64, and websocket examples.

errors

tts errors come back as json with an error message and a code:

{ "error": "text has nothing to speak", "code": "INVALID_TEXT" }

status	`code`	what happened
400	`INVALID_TEXT`	`text` has nothing to speak: empty, whitespace, punctuation only or emoji only (no letter or digit in any script). not charged.
400	`UNSUPPORTED_AUDIO_FORMAT`	`audio_format` is `null` or not a supported value. see audio formats.
422	`VALIDATION_ERROR`	a field is missing or malformed.

the 400s above apply to the two http synthesis routes, POST /v1/tts and POST /v1/tts/json. POST /v1/tts/ws-connect shares UNSUPPORTED_AUDIO_FORMAT and the 422, but does not check the text when it mints: unspeakable text is reported on the socket as an INVALID_TEXT error frame; see streaming. a 422 names the failing field and does not echo your request back:

{
  "error": "text: Field required",
  "code": "VALIDATION_ERROR",
  "detail": [{ "type": "missing", "loc": ["body", "text"], "msg": "Field required" }]
}

try the api reference playground to call the endpoint with your own key right from the docs.

next: stream audio in real time or build a voice agent with pipecat.

documentation

sdk

integrations

cookbook

api reference

1. get an api key

generate an api key

2. pick a model

3. synthesize speech

choose another audio format

errors

​1. get an api key

generate an api key

​2. pick a model

​3. synthesize speech

​choose another audio format

​errors

1. get an api key

2. pick a model

3. synthesize speech

choose another audio format

errors